Cloud data sharing method and system for supply chain

Abstract

The invention discloses a cloud data sharing method and system for a supply chain, and particularly relates to the technical field of data sharing: collecting data from systems of a plurality of participants of the supply chain in real time, carrying out standardization processing, uploading the data to a cloud platform, then extracting updating frequency characteristics and synchronous matching characteristics of the data, and carrying out data sharing; the method comprises the following steps: constructing a prediction model, carrying out weighted calculation on data, finally obtaining an overall accuracy coefficient, and dividing the data into high, medium and low classes according to the comparison of the coefficient and a gradient standard threshold: the high-accuracy data is directly used for decision making, and the low-accuracy data is stopped from being used and is required to be re-recorded; and the middle-accuracy data is further analyzed and the sharing strategy is dynamically adjusted, and the accuracy and consistency of the data are improved, so that the decision-making efficiency of the supply chain is optimized, the inventory management and production plan problems caused by data errors are reduced, and the overall operation efficiency of the supply chain is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data sharing, and in particular to a cloud data sharing method and system for supply chain. Background Art

[0002] Cloud data sharing in the supply chain refers to the centralized storage, management and sharing of key data in the supply chain through a cloud computing platform, so that all participants (such as suppliers, manufacturers, distributors and retailers) can access and update information in real time. This method breaks the information island situation in each link of the traditional supply chain and achieves more efficient data transmission and collaboration. Through cloud sharing, data flow in the supply chain is more transparent, information delays are reduced, and the response speed to market changes is improved, thereby optimizing overall operations.

[0003] The prior art has the following deficiencies:

[0004] Cloud data sharing relies on multiple supply chain participants to upload and update data in a timely and accurate manner. However, if the data is not entered accurately, it will lead to distorted information and affect the decision-making of the entire supply chain. For example, suppliers may not update inventory data in a timely manner, causing manufacturers to mistakenly believe that materials are sufficient, resulting in orders not being delivered on time. Inaccurate data will directly affect inventory management. For example, if inventory data in the supply chain is not updated in a timely manner, manufacturers or retailers may not be able to obtain real-time inventory information. Manufacturers may mistakenly believe that inventory is insufficient, resulting in overproduction or procurement, increasing warehousing and management costs, and occupying funds and resources. If the inventory information in the supply chain fails to reflect the actual situation in a timely manner, it may lead to inventory shortages, affect production plans, fail to meet customer needs, and thus lose sales opportunities, or even lead to order cancellations. Summary of the invention

[0005] The purpose of the present invention is to provide a cloud data sharing method and system for supply chain to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a cloud data sharing method for supply chain, comprising the following steps:

[0007] S1; collect relevant data in the supply chain from the systems of several supply chain participants in real time, standardize the collected data, and upload the processed data to the cloud platform for centralized storage;

[0008] S2: Extract features of relevant data in the supply chain on the cloud platform, and extract update frequency features and synchronization matching features of relevant data in the supply chain in different time periods;

[0009] S3: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation;

[0010] S4: Compare the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divide the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data;

[0011] S5: For data with high accuracy, use it directly for supply chain decision-making; for data with low accuracy, stop using it in the automated decision-making system immediately, and re-record and update it; for data with medium accuracy, conduct in-depth analysis of its accuracy and dynamically adjust the sharing strategy based on the analysis results.

[0012] Preferably, in S2, an update frequency anomaly index is generated according to the extracted update frequency characteristic value, and the method for obtaining the update frequency anomaly index is:

[0013] Divide the time into T time periods, denoted by T i , where i represents the time period number and the update frequency characteristic value is marked as U i,j , that is, in the time period T i The number of times supply chain participant j uploads data represents the frequency of data upload by each participant in the T time period; the historical average update frequency is obtained from the historical data That is, the average update frequency of supply chain participant j in the past n time periods, expressed as: Where n is the number of selected historical time periods, and the fluctuation value GF of the update frequency is calculated as follows: Calculate the degree to which the update frequency of supply chain participants deviates from their historical average value during the T period, that is, calculate the update frequency anomaly value, and the expression is: Where FD is the update frequency anomaly value. If the update frequency anomaly value is greater than 0, it means that the update frequency of this time period is higher than the historical average level, and the degree of anomaly is high. The update frequency anomaly values ​​greater than 0 are used to establish a data set, and the update frequency anomaly index is calculated. The expression is: KL = 1-e -s|FD| ; In the formula, s is the adjustment coefficient and KL is the update frequency abnormality index.

[0014] Preferably, in S2, a matching rate deviation value is generated according to the extracted synchronous matching feature, and the matching rate deviation value is obtained by:

[0015] The time in the supply chain operation process is divided into several time periods, denoted as M q, where q represents the time period number, and the data set of the supply chain participants is marked as D i,j , that is, in time period M q In the above example, the relevant dataset uploaded by the supply chain participant p is marked as R. i,p,e , indicating that in time period M q The number of entries that successfully match between the datasets of supply chain participants p and e is the total dataset H i,p,e , that is, in time period M q The total amount of data in the relevant data sets of supply chain participants p and e is used to calculate the matching rate of the two parties' data; the synchronization matching rate Z is calculated. i,p,e , the synchronization matching rate represents the time period M q The success rate of data synchronization between supply chain participants q and e is calculated as follows: Calculate the mean of the synchronization matching rate respectively and standard deviation σ p,e , and then analyze it to calculate the matching rate deviation value, the expression is: Where FG is the matching rate deviation value.

[0016] Preferably, in S3, a data prediction model is constructed, and weight assignments of relevant data in the supply chain in different time periods are determined according to the extracted update frequency features and synchronization matching features, and the overall accuracy coefficient of the relevant data in the supply chain is calculated after performing weighted average calculations on the weighted averages;

[0017] The update frequency anomaly index and the matching rate deviation value are normalized, and the weight assignment of relevant data in the supply chain in different time periods is calculated by the normalized update frequency anomaly index and the matching rate deviation value. The overall accuracy coefficient of the relevant data in the supply chain is calculated after weighted average calculation.

[0018] Preferably, in S4, the calculated overall accuracy coefficient of the relevant data in the supply chain is compared with the gradient standard threshold, and the accuracy of the relevant data in the supply chain is divided into different levels, namely, high accuracy data, medium accuracy data and low accuracy data;

[0019] Compare the overall accuracy coefficient of the acquired relevant data in the supply chain with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the overall accuracy coefficient of the relevant data in the supply chain with the first standard threshold and the second standard threshold respectively;

[0020] If the overall accuracy coefficient of the relevant data in the supply chain is greater than the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is high, and a high-accuracy data signal is generated at this time, and the data is classified as high-accuracy data;

[0021] If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is average, and a medium accuracy data signal is generated at this time, and it is classified as medium accuracy data;

[0022] If the overall accuracy coefficient of the relevant data in the supply chain is less than the first standard threshold, it means that the overall accuracy of the relevant data in the supply chain is low. At this time, a low-accuracy data signal is generated and classified as low-accuracy data.

[0023] Preferably, in S5, for the medium accuracy data, its accuracy is deeply analyzed, and the sharing strategy is dynamically adjusted according to the analysis results, specifically:

[0024] If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it will be classified as medium-accuracy data, and the overall accuracy coefficients generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold will be collected, and a corresponding data set will be established. The mean and standard deviation of the data set will be calculated, and after analyzing it, the sharing strategy will be dynamically adjusted according to the analysis results.

[0025] Preferably, if the mean of the overall accuracy coefficient in the data set is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, it is said that the accuracy of the data set is high and the fluctuation is small, and the current data sharing strategy is maintained without making any adjustments;

[0026] If the mean of the overall accuracy coefficient is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is greater than or equal to the reference threshold of the standard deviation of the overall accuracy coefficient, it means that although the accuracy of the data set is high, the fluctuation is large. Optimize the data update frequency, reduce fluctuations, and ensure data stability;

[0027] If the overall accuracy coefficient mean is less than the reference threshold of the overall accuracy coefficient mean, and the overall accuracy coefficient standard deviation is greater than or equal to the reference threshold of the overall accuracy coefficient standard deviation, it means that the data accuracy is low and the fluctuation is large. Data correction should be given priority, and the sharing strategy should be adjusted dynamically to improve data quality.

[0028] If the mean of the overall accuracy coefficient is less than the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, it means that the data accuracy is low but the fluctuation is small. Strengthen data verification and improve the accuracy of data entry.

[0029] The present invention also provides a cloud data sharing system for supply chain, including a data acquisition module, a feature extraction module, a weight assignment module, a data partitioning module and a sharing processing module;

[0030] Data collection module: collects relevant data in the supply chain from the systems of several supply chain participants in real time, standardizes the collected data, and uploads the processed data to the cloud platform for centralized storage;

[0031] Feature extraction module: extracts features from relevant data in the supply chain on the cloud platform, and extracts update frequency features and synchronization matching features of relevant data in the supply chain in different time periods;

[0032] Weight assignment module: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation;

[0033] Data division module: compares the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divides the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data;

[0034] Shared processing module: For data with high accuracy, it is directly used for supply chain decision-making; for data with low accuracy, its use in the automated decision-making system should be stopped immediately, and it should be re-recorded and updated; for data with medium accuracy, its accuracy should be deeply analyzed, and the sharing strategy should be dynamically adjusted according to the analysis results.

[0035] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0036] 1. The present invention collects relevant data of all participants in the supply chain in real time and performs standardized processing. The system can automatically extract the update frequency characteristics and synchronization matching characteristics of the data, build a data prediction model and calculate the overall accuracy coefficient. By grading the accuracy coefficient of the supply chain data, the system divides the data into high, medium and low accuracy, and adopts corresponding decision-making processing strategies according to different accuracy levels, which are directly used for decision-making, stopping use and re-recording data, or conducting in-depth analysis and dynamically adjusting sharing strategies. This method improves the real-time and consistency of supply chain data, ensures that all links in the supply chain can make decisions based on reliable data, and reduces inventory management, production planning and order delivery problems caused by data errors.

[0037] 2. The present invention can dynamically monitor and optimize the data quality in the supply chain by calculating the update frequency anomaly index and the matching rate deviation value. When the data accuracy coefficient fluctuates greatly, the system will automatically adjust the data update frequency or trigger data correction to improve the overall data quality. When the accuracy coefficient is low but the fluctuation is small, the system will strengthen the data verification process to ensure the accuracy of future data entry, which not only ensures the continuous improvement of supply chain data quality, but also reduces operational risks, optimizes supply chain management efficiency, and improves the overall stability and competitiveness of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0039] Figure 1 The figure is a flow chart of the method of the present invention.

[0040] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Example 1, please refer to Figure 1 As shown, the cloud data sharing method for supply chain described in this embodiment includes the following steps:

[0043] S1; collect relevant data in the supply chain from the systems of several supply chain participants in real time, standardize the collected data, and upload the processed data to the cloud platform for centralized storage;

[0044] S2: Extract features of relevant data in the supply chain on the cloud platform, and extract update frequency features and synchronization matching features of relevant data in the supply chain in different time periods;

[0045] S3: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation;

[0046] S4: Compare the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divide the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data;

[0047] S5: For data with high accuracy, use it directly for supply chain decision-making; for data with low accuracy, stop using it in the automated decision-making system immediately, and re-record and update it; for data with medium accuracy, conduct in-depth analysis of its accuracy and dynamically adjust the sharing strategy based on the analysis results.

[0048] Among them, in S1, relevant data in the supply chain are collected in real time from the systems of several supply chain participants, and the collected data are standardized and uploaded to the cloud platform for centralized storage.

[0049] Identify and determine the data sources of each participant in the supply chain, including suppliers, manufacturers, distributors, logistics providers, retailers, etc. The data source can be ERP (Enterprise Resource Planning), WMS (Warehouse Management System), MES (Manufacturing Execution System), etc. Determine the type of data that needs to be collected, such as order data, inventory data, production plans, logistics information, etc. Ensure that the necessary data for key links in the supply chain are covered. Through technical means such as API (Application Programming Interface) or EDI (Electronic Data Interchange), establish an interface between the supply chain participant system and the cloud platform to realize automatic data collection. The system of each participant needs to upload data to the cloud platform through the interface regularly or in real time. Real-time collection mechanism: Set up scheduled tasks or triggers to automatically collect data at specific time intervals (such as every hour) or when key events (such as order creation, inventory changes) occur.

[0050] Since the systems used by different parties are different, the data formats may be different (such as CSV, JSON, XML, etc.), so the collected data needs to be uniformly converted into a standard format. Use conversion tools or middleware to ensure that all data is transmitted to the cloud platform in a unified format. After the data of each participant is standardized, it is uploaded to the cloud platform for storage through a preset interface. The cloud platform receives and stores the processed data to ensure the accessibility and traceability of the data. The cloud platform classifies and stores the data according to the data type (such as inventory, order, logistics, etc.) to ensure that each type of data can be managed independently and retrieved efficiently. The table structure of the database is designed according to the hierarchical structure of the supply chain, and the data of suppliers, manufacturers, distributors, etc. are partitioned and managed by level or region to ensure the orderly storage of data. During the upload process, the security of data transmission is ensured through encryption protocols (such as SSL / TLS) to prevent data from being intercepted or tampered with during transmission. Set independent access rights for each supply chain participant in the cloud platform to ensure that each participant can only access and operate the data to which it has permission.

[0051] S2: Extract features of relevant data in the supply chain on the cloud platform, and extract the update frequency features and synchronization matching features of relevant data in the supply chain in different time periods.

[0052] By extracting features from supply chain data on the cloud platform and analyzing the update frequency features and synchronization matching features in different time periods, it can help monitor the timeliness and consistency of data in real time, quickly discover data delays or inconsistencies, thereby improving data accuracy and reliability, ensuring that all parties in the supply chain make decisions based on the latest and accurate information, and reducing the occurrence of problems such as inventory errors, production plan deviations, and logistics delays.

[0053] Extract relevant data of all supply chain participants (such as suppliers, manufacturers, logistics parties, etc.) from the cloud platform, including inventory data, order data, production data, logistics data, etc. Clean the extracted data to remove duplicate data, outliers, and missing data. Ensure that each piece of data has a clear timestamp and source information.

[0054] According to business needs, divide time into different periods, such as daily, weekly, monthly, etc., or set time periods according to important nodes of the supply chain (such as order generation, inventory changes). Statistics are collected on data updates in each time period, and the frequency of data upload by each supply chain participant in the time period is calculated. Calculate the number of data entries uploaded in each time period. Compare the timestamp of the latest data in the time period with the timestamp of the previous time period, and calculate the interval between data update times. Calculate the data update frequency of each supply chain participant and generate the corresponding update frequency characteristic value.

[0055] The update frequency anomaly index is generated according to the extracted update frequency characteristic value, and the method for obtaining the update frequency anomaly index is:

[0056] Divide the time into T time periods, denoted by T i , where i represents the time period number and the update frequency characteristic value is marked as U i,j , that is, in the time period T i The number of times supply chain participant j uploads data represents the frequency of data upload by each participant in the T time period; the historical average update frequency is obtained from the historical data That is, the average update frequency of supply chain participant j in the past n time periods, expressed as: Where n is the number of selected historical time periods, and the fluctuation value GF of the update frequency is calculated as follows: Calculate the degree to which the update frequency of supply chain participants deviates from their historical average value during the T period, that is, calculate the update frequency anomaly value, and the expression is: Where FD is the update frequency anomaly value. If the update frequency anomaly value is greater than 0, it means that the update frequency of this time period is higher than the historical average level, and the degree of anomaly is high. The update frequency anomaly values ​​greater than 0 are used to establish a data set, and the update frequency anomaly index is calculated. The expression is: KL = 1-e -s|FD| ; In the formula, s is the adjustment coefficient, which is used to control the sensitivity of the abnormal index. Usually, s ranges from 0.1 to 0.5. The larger the value, the more sensitive the abnormal index. KL is the update frequency abnormal index.

[0057] The larger the update frequency anomaly index is, the lower the accuracy of the relevant data in the supply chain is. This indicates that the data upload frequency of each supply chain participant deviates greatly from the historical average level, which may mean that the data is not updated in time or the upload frequency is too low, resulting in delayed or incomplete data. This abnormal situation will cause supply chain decisions to be based on outdated or inaccurate information, increase the risk of errors in inventory management, production planning and logistics scheduling, and thus affect the operating efficiency and reliability of the entire supply chain.

[0058] Select key data in the supply chain (such as inventory, order quantity, and delivery time) for cross-system comparison to check whether the data of different supply chain participants is consistent in the same time period. For example, check whether the supplier's inventory records match the manufacturer's purchase order data. Compare the logistics party's delivery time and the manufacturer's order status data.

[0059] The consistency of data is calculated through matching algorithms to determine the matching degree of data uploaded by different systems in terms of quantity, time and status. The following methods can be used: Use similarity calculations (such as Jaccard similarity coefficient) to quantify the matching degree between two sets of data. Count the number of matching items and calculate the matching rate (such as whether the inventory quantity is consistent, whether the delivery and order status are consistent, etc.).

[0060] The matching rate deviation value is generated according to the extracted synchronous matching features, and the matching rate deviation value is obtained by:

[0061] The time in the supply chain operation process is divided into several time periods, denoted as M q , where q represents the time period number, and the data set of the supply chain participants is marked as D i,j , that is, in time period M q In the case of a supply chain participant p, a certain type of related data set (such as inventory, order or logistics data) is uploaded. The matching data set is marked as R i,p,e , indicating that in time period M q The number of entries that successfully match between the datasets of supply chain participants p and e is the total dataset H i,p,e , that is, in time period M q The total amount of data in the relevant data sets of supply chain participants p and e is used to calculate the matching rate of the two parties' data; the synchronization matching rate Z is calculated. i,p,e , the synchronization matching rate represents the time period M q The success rate of data synchronization between supply chain participants q and e is calculated as follows: Calculate the mean of the synchronization matching rate respectively and standard deviation σ p,e , and then analyze it to calculate the matching rate deviation value, the expression is: Where FG is the matching rate deviation value.

[0062] The larger the matching rate deviation value, the lower the accuracy of the relevant data in the supply chain. This means that there is a large degree of asynchrony or inconsistency in the data between different supply chain participants, causing the data matching rate to deviate from the historical average level. A large deviation value means that the data may have problems such as input errors, delayed updates, or inconsistent data sources, which in turn makes decisions in the supply chain based on unreliable information, increases the risk of errors in inventory management, production planning, and logistics scheduling, and affects the efficiency and stability of the overall supply chain.

[0063] S3: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculations.

[0064] The update frequency anomaly index and the matching rate deviation value are normalized, and the weight assignment of relevant data in the supply chain in different time periods is calculated by the normalized update frequency anomaly index and the matching rate deviation value. The overall accuracy coefficient of the relevant data in the supply chain is calculated after weighted average calculation.

[0065] For example, the present invention can use the following data prediction model formula to calculate the weight assignment of relevant data in the supply chain in different time periods, and the calculation expression is: Where LK is the weight assignment of relevant data in the supply chain in different time periods, KL is the update frequency anomaly index, FG is the matching rate deviation value, a1 and a2 are the proportional coefficients of the update frequency anomaly index and the matching rate deviation value, and a2>a1>0.

[0066] S4: Compare the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divide the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data.

[0067] Compare the overall accuracy coefficient of the acquired relevant data in the supply chain with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the overall accuracy coefficient of the relevant data in the supply chain with the first standard threshold and the second standard threshold respectively;

[0068] If the overall accuracy coefficient of the relevant data in the supply chain is greater than the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is high, and a high-accuracy data signal is generated at this time, and the data is classified as high-accuracy data;

[0069] If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is average, and a medium accuracy data signal is generated at this time, and it is classified as medium accuracy data;

[0070] If the overall accuracy coefficient of the relevant data in the supply chain is less than the first standard threshold, it means that the overall accuracy of the relevant data in the supply chain is low. At this time, a low-accuracy data signal is generated and classified as low-accuracy data.

[0071] S5: For data with high accuracy, use it directly for supply chain decision-making; for data with low accuracy, stop using it in the automated decision-making system immediately, and re-record and update it; for data with medium accuracy, conduct in-depth analysis of its accuracy and dynamically adjust the sharing strategy based on the analysis results.

[0072] For data classified as high accuracy, the system can directly use it for supply chain decision-making, such as production planning, inventory management, and logistics scheduling, because the data is frequently and stably updated and has historically been highly matched with the data of other supply chain participants. The data does not need to be further verified and is automatically incorporated into various decision-making processes of the supply chain. For example, manufacturers can formulate production plans based on high-accuracy inventory data to ensure sufficient material supply and prevent misjudgments or production interruptions. Due to the high reliability of high-accuracy data, it can quickly support automated processes and improve the overall operating efficiency of the supply chain.

[0073] Low-accuracy data cannot be directly used in the supply chain's automated decision-making system due to serious update delays, data inconsistencies or entry errors. If the data continues to be used, it may lead to major errors in supply chain decision-making. Therefore, it is necessary to immediately stop using it in the automated process and re-enter or update it. After the system detects low-accuracy data, it should immediately stop using the data in the automated decision-making system to prevent incorrect data from causing misleading decisions. For example, manufacturers should avoid making production plans based on incorrect inventory data. Notify supply chain participants: The system will automatically send notifications to relevant supply chain participants, requiring them to re-check and update low-accuracy data. Supply chain participants re-enter or upload the latest data based on actual conditions and resubmit it to the cloud platform for verification. The system compares the newly uploaded data with historical data or other data sources to ensure that the corrected data is accurate and timely. If there are still abnormalities in the data, a verification request will be issued again until the data meets the requirements. By promptly stopping the use of low-accuracy data and forcing re-entry, decision-making errors caused by data errors can be avoided and the risks of supply chain operations can be reduced.

[0074] For medium-accuracy data, we conduct in-depth analysis of its accuracy and dynamically adjust the sharing strategy based on the analysis results. Specifically:

[0075] If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it will be classified as medium-accuracy data, and the overall accuracy coefficients generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold will be collected, and a corresponding data set will be established. The mean and standard deviation of the data set will be calculated, and after analyzing it, the sharing strategy will be dynamically adjusted according to the analysis results.

[0076] If the mean of the overall accuracy coefficient in the data set is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, the accuracy of the data set is high and the fluctuation is small, and the data is stable and reliable. The current data sharing strategy can be maintained without making adjustments;

[0077] If the mean of the overall accuracy coefficient is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is greater than or equal to the reference threshold of the standard deviation of the overall accuracy coefficient, it means that although the accuracy of the data set is high, the fluctuation is large, and there are problems with the stability of the data. The frequency of data updates should be optimized or monitoring should be strengthened to reduce fluctuations and ensure data stability;

[0078] If the overall accuracy coefficient mean is less than the reference threshold of the overall accuracy coefficient mean, and the overall accuracy coefficient standard deviation is greater than or equal to the reference threshold of the overall accuracy coefficient standard deviation, it means that the data accuracy is low and fluctuates greatly, indicating that the data quality is poor and unstable. Data correction or mandatory update should be prioritized, and the sharing strategy should be adjusted dynamically to improve data quality;

[0079] If the mean of the overall accuracy coefficient is less than the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, it means that the data accuracy is low but the fluctuation is small, which means that the data is stable but the quality is insufficient. Data verification should be strengthened to improve the accuracy of data entry or the timeliness of update.

[0080] In this embodiment, relevant data is collected in real time from the systems of all parties involved in the supply chain, and the data is standardized and uploaded to the cloud platform for centralized storage. Next, a data prediction model is constructed by extracting the data update frequency characteristics and synchronization matching characteristics in different time periods, and a weighted average calculation is performed based on these characteristics to obtain the overall accuracy coefficient of the supply chain data. Then, the overall accuracy coefficient is compared with the preset gradient standard threshold, and the data is divided into three categories: high accuracy, medium accuracy, and low accuracy. For high-accuracy data, it is directly used for supply chain decision-making; for low-accuracy data, its use in automated decision-making is stopped and re-recorded and updated; and for medium-accuracy data, its accuracy is deeply analyzed, and the data sharing strategy is dynamically adjusted according to the analysis results to ensure the efficient operation of the supply chain.

[0081] Example 2, please refer to Figure 2 As shown, the cloud data sharing system for supply chain described in this embodiment includes a data acquisition module, a feature extraction module, a weight assignment module, a data partitioning module and a sharing processing module;

[0082] Data collection module: collects relevant data in the supply chain from the systems of several supply chain participants in real time, standardizes the collected data, and uploads the processed data to the cloud platform for centralized storage;

[0083] Feature extraction module: extracts features from relevant data in the supply chain on the cloud platform, and extracts update frequency features and synchronization matching features of relevant data in the supply chain in different time periods;

[0084] Weight assignment module: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation;

[0085] Data division module: compares the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divides the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data;

[0086] Shared processing module: For data with high accuracy, it is directly used for supply chain decision-making; for data with low accuracy, its use in the automated decision-making system should be stopped immediately, and it should be re-recorded and updated; for data with medium accuracy, its accuracy should be deeply analyzed, and the sharing strategy should be dynamically adjusted according to the analysis results.

[0087] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0088] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0089] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0090] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0091] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0092] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A cloud data sharing method for supply chain, characterized by: The steps include: S1； Collect relevant data in the supply chain from the systems of several supply chain participants in real time, standardize the collected data, and upload the processed data to the cloud platform for centralized storage; S2: Extract features of relevant data in the supply chain on the cloud platform, and extract update frequency features and synchronization matching features of relevant data in the supply chain in different time periods; S3: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation; S4: Compare the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divide the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data; S5: For data with high accuracy, use it directly for supply chain decision-making; for data with low accuracy, stop using it in the automated decision-making system immediately, and re-record and update it; for data with medium accuracy, conduct in-depth analysis of its accuracy and dynamically adjust the sharing strategy based on the analysis results.

2. A cloud data sharing method for supply chain according to claim 1, characterized in that: In S2, an update frequency anomaly index is generated according to the extracted update frequency characteristic value, and the method for obtaining the update frequency anomaly index is: Divide the time into T time periods, denoted by T i , where i represents the time period number and the update frequency characteristic value is marked as U i,j , that is, in the time period T i The number of times supply chain participant j uploads data represents the frequency of data upload by each participant in the T time period; the historical average update frequency is obtained from the historical data That is, the average update frequency of supply chain participant j in the past n time periods, expressed as: Where n is the number of selected historical time periods, and the fluctuation value GF of the update frequency is calculated as follows: Calculate the degree to which the update frequency of supply chain participants deviates from their historical average value during the T period, that is, calculate the update frequency anomaly value, and the expression is: Where FD is the update frequency anomaly value. If the update frequency anomaly value is greater than 0, it means that the update frequency of this time period is higher than the historical average level, and the degree of anomaly is high. The update frequency anomaly values ​​greater than 0 are used to establish a data set, and the update frequency anomaly index is calculated. The expression is: KL = 1-e -s | FD |; where s is the adjustment coefficient and KL is the update frequency anomaly index.

3. A cloud data sharing method for supply chain according to claim 2, characterized in that: In S2, a matching rate deviation value is generated according to the extracted synchronous matching features, and the matching rate deviation value is obtained by: The time in the supply chain operation process is divided into several time periods, denoted as M q , where q represents the time period number, and the data set of the supply chain participants is marked as D i,j , that is, in time period M q In, the relevant data set uploaded by the supply chain participant p; Label the matching dataset as R i,p,e , indicating that in time period M q The number of entries that successfully match between the datasets of supply chain participants p and e is the total dataset H i,p,e , that is, in time period M q The total amount of data in the relevant data sets of supply chain participant p and supply chain participant e is used to calculate the matching rate of the two parties’ data; Calculate the synchronization matching rate Z i,p,e , the synchronization matching rate represents the time period M q The success rate of data synchronization between supply chain participants q and e is calculated as follows: Calculate the mean of the synchronization matching rate respectively and standard deviation σ p,e , and then analyze it to calculate the matching rate deviation value, the expression is: Where FG is the matching rate deviation value.

4. A cloud data sharing method for supply chain according to claim 3, characterized in that: In S3, a data prediction model is constructed to determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and the overall accuracy coefficient of the relevant data in the supply chain is calculated after performing a weighted average calculation; The update frequency anomaly index and the matching rate deviation value are normalized, and the weight assignment of relevant data in the supply chain in different time periods is calculated by the normalized update frequency anomaly index and the matching rate deviation value. The overall accuracy coefficient of the relevant data in the supply chain is calculated after weighted average calculation.

5. A cloud data sharing method for supply chain according to claim 4, characterized in that: In S4, the calculated overall accuracy coefficient of the relevant data in the supply chain is compared with the gradient standard threshold, and the accuracy of the relevant data in the supply chain is divided into different levels, namely, high accuracy data, medium accuracy data and low accuracy data; Compare the overall accuracy coefficient of the acquired relevant data in the supply chain with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and compare the overall accuracy coefficient of the relevant data in the supply chain with the first standard threshold and the second standard threshold respectively; If the overall accuracy coefficient of the relevant data in the supply chain is greater than the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is high, and a high-accuracy data signal is generated at this time, and the data is classified as high-accuracy data; If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the overall accuracy of the relevant data in the supply chain is average, and a medium accuracy data signal is generated at this time, and it is classified as medium accuracy data; If the overall accuracy coefficient of the relevant data in the supply chain is less than the first standard threshold, it means that the overall accuracy of the relevant data in the supply chain is low. At this time, a low-accuracy data signal is generated and classified as low-accuracy data.

6. The cloud data sharing method for supply chain according to claim 1, characterized in that: In S5, for medium accuracy data, its accuracy is deeply analyzed, and the sharing strategy is dynamically adjusted according to the analysis results, specifically: If the overall accuracy coefficient of the relevant data in the supply chain is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it will be classified as medium-accuracy data, and the overall accuracy coefficients generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold will be collected, and a corresponding data set will be established. The mean and standard deviation of the data set will be calculated, and after analyzing it, the sharing strategy will be dynamically adjusted according to the analysis results.

7. A cloud data sharing method for supply chain according to claim 6, characterized in that: If the mean of the overall accuracy coefficient in the data set is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, the accuracy of the data set is high and the fluctuation is small, and the current data sharing strategy is maintained without making any adjustments; If the mean of the overall accuracy coefficient is greater than or equal to the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is greater than or equal to the reference threshold of the standard deviation of the overall accuracy coefficient, it means that although the accuracy of the data set is high, the fluctuation is large. Optimize the data update frequency, reduce fluctuations, and ensure data stability; If the overall accuracy coefficient mean is less than the reference threshold of the overall accuracy coefficient mean, and the overall accuracy coefficient standard deviation is greater than or equal to the reference threshold of the overall accuracy coefficient standard deviation, it means that the data accuracy is low and the fluctuation is large. Data correction should be given priority, and the sharing strategy should be adjusted dynamically to improve data quality. If the mean of the overall accuracy coefficient is less than the reference threshold of the mean of the overall accuracy coefficient, and the standard deviation of the overall accuracy coefficient is less than the reference threshold of the standard deviation of the overall accuracy coefficient, it means that the data accuracy is low but the fluctuation is small. Strengthen data verification and improve the accuracy of data entry.

8. A cloud data sharing system for supply chain, used to implement a cloud data sharing method for supply chain according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, feature extraction module, weight assignment module, data partitioning module and shared processing module; Data collection module: collects relevant data in the supply chain from the systems of several supply chain participants in real time, standardizes the collected data, and uploads the processed data to the cloud platform for centralized storage; Feature extraction module: extracts features from relevant data in the supply chain on the cloud platform, and extracts update frequency features and synchronization matching features of relevant data in the supply chain in different time periods; Weight assignment module: Build a data prediction model, determine the weight assignment of relevant data in the supply chain in different time periods based on the extracted update frequency characteristics and synchronization matching characteristics, and calculate the overall accuracy coefficient of the relevant data in the supply chain after performing weighted average calculation; Data division module: compares the calculated overall accuracy coefficient of the relevant data in the supply chain with the gradient standard threshold, and divides the accuracy of the relevant data in the supply chain into different levels, namely, high accuracy data, medium accuracy data and low accuracy data; Shared processing module: For data with high accuracy, it is directly used for supply chain decision-making; for data with low accuracy, its use in the automated decision-making system should be stopped immediately, and it should be re-recorded and updated; for data with medium accuracy, its accuracy should be deeply analyzed, and the sharing strategy should be dynamically adjusted according to the analysis results.

Images